Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 17406
    Prev
    Next
    INDEX
    Explanations

    information related to ticket sales and event details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utsch
    -0.15
    mez
    -0.14
    usercontent
    -0.14
     ServiceProvider
    -0.14
    æ°¸ä¹ħ
    -0.13
    ietf
    -0.13
    _ASSUME
    -0.13
    á»ı
    -0.13
    SSI
    -0.13
    attended
    -0.13
    POSITIVE LOGITS
     pres
    0.28
     Ticket
    0.23
     sale
    0.22
    -sale
    0.21
     general
    0.21
     Pres
    0.20
    Reserved
    0.20
     Reserved
    0.20
     Tickets
    0.20
     advance
    0.19
    Activations Density 0.021%

    No Known Activations